• Jegan Amarnath.J
• Nivetha.K.J
• Pavithra.J
• Geetha.P

A bot is a piece of software that completes automated task over the internet .On social media the prevalence of bot is ubiquitous. Nearly 48 million twitter accounts are automated using bots. Detecting bots is necessary in order to identify bad actors in “Twitter verse” and protect genuine users from misinformation and malicious intents. According to a study released by Pew Research Center, these bots contribute to approximately 66% of total tweets in twitter.Bots are becoming smarter, they mimic humans to avoid being detected and suspended, and increase throughput by creating many accounts.The idea is to develop a bot detection algorithm to identify twitter bot accounts by using attributes like followers _ count, no of tweets or likes, status _ count etc. Thus evaluate these features using k-nearest neighbour algorithm and Random Forest. Finally the result of two models are combined using suitable ensemble method to produce more accurate solution. The Test dataset is prepared specifically for any hashtag. The dataset consists details of the accounts which uses that hashtag. This dataset is cleaned and used as a test dataset.

Twitter Bot detection, Hashtag, KNN, Random Forest, Evaluation module.

"IDENTIFYING TWITTER BOTS BASED ON TRENDING HASHTAGS USING MACHINE LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.151-156, June 2019, Available :http://www.jetir.org/papers/JETIRDF06030.pdf

"IDENTIFYING TWITTER BOTS BASED ON TRENDING HASHTAGS USING MACHINE LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp151-156, June 2019, Available at : http://www.jetir.org/papers/JETIRDF06030.pdf